158 citations · 1k across the 37 of their papers we have counts for
6 papers · 1 filter
End-to-end Triplet Loss based Emotion Embedding System for Speech Emotion Recognition
Puneet Kumar, Sidharth Jain, Balasubramanian Raman +2
In this paper, an end-to-end neural embedding system based on triplet loss and residual learning has been proposed for speech emotion recognition. The proposed system learns the em…
Position and Rotation Invariant Sign Language Recognition from 3D Kinect Data with Recurrent Neural Networks
Prasun Roy, Saumik Bhattacharya, Partha Pratim Roy +1
Sign language is a gesture-based symbolic communication medium among speech and hearing impaired people. It also serves as a communication bridge between non-impaired and impaired…
Fast Griffin Lim based Waveform Generation Strategy for Text-to-Speech Synthesis
Ankit Sharma, Puneet Kumar, Vikas Maddukuri +5
The performance of text-to-speech (TTS) systems heavily depends on spectrogram to waveform generation, also known as the speech reconstruction phase. The time required for the same…
UDBNET: Unsupervised Document Binarization Network via Adversarial Game
Amandeep Kumar, Shuvozit Ghose, Pinaki Nath Chowdhury +2
Degraded document image binarization is one of the most challenging tasks in the domain of document image analysis. In this paper, we present a novel approach towards document imag…
Modeling Extent-of-Texture Information for Ground Terrain Recognition
Shuvozit Ghose, Pinaki Nath Chowdhury, Partha Pratim Roy +1
Ground Terrain Recognition is a difficult task as the context information varies significantly over the regions of a ground terrain image. In this paper, we propose a novel approac…
Understanding Crowd Flow Movements Using Active-Langevin Model
Shreetam Behera, Debi Prosad Dogra, Malay Kumar Bandyopadhyay +1
Crowd flow describes the elementary group behavior of crowds. Understanding the dynamics behind these movements can help to identify various abnormalities in crowds. However, devel…